87 Hits in 3.0 sec

On Benchmarking of Invoice Analysis Systems [chapter]

Bertin Klein, Stefan Agne, Andreas Dengel
2006 Lecture Notes in Computer Science  
The state of the art of benchmarking of document analysis systems is presented, based on the processing levels: Document Page Segmentation, Text Recognition, Document Classification, and Information Extraction  ...  An approach is presented to guide the benchmarking of invoice analysis systems, a specific, applied subclass of document analysis systems.  ...  Document Page Segmentation Two main classes of approaches for the benchmarking of document page segmentation can be distinguished in the literature: bitmap based approaches that operate at pixel level  ... 
doi:10.1007/11669487_28 fatcat:vollb74orzewxhu5ty3cfvqalq

Document image analysis: What is missing? [chapter]

George Nagy
1995 Lecture Notes in Computer Science  
The realization that accurate document image analysis requires fairly specific pre-stored information has resulted in the investigation of new data structures for knowledge bases and for the representation  ...  Driven partly by document distribution on CD-ROM and via the World Wide Web, there is more interest in the preservation of layout and format attributes to increase legibility (sometimes called "page reconstruction  ...  This work has been conducted in the New York State Center for Advanced Technology (CAT) in Manufacturing, Automation and Robotics, which is partially funded by a block grant from the New York.  ... 
doi:10.1007/3-540-60298-4_317 fatcat:nqgzemstcfhnpitdrsecr6a4du

Bridging the paper and electronic worlds

Walter Johnson, Herbert Jellinek, Leigh Klotz, Ramana Rao, Stuart K. Card
1993 Proceedings of the SIGCHI conference on Human factors in computing systems - CHI '93  
Despite these advantages, paper remains a second class citizen in the electronic world. In this paper, we present a new technology for bridging the paper and the electronic worlds.  ...  In the new technology, the user interface moves beyond the workstation and onto paper itself. We describe paper user interface technology and its implementation in a particular system called XAX.  ...  Characters and fonta that can be recognized in an clean 400 spot-per-inch image become unrecognizable in a skewed and stretched 200x1CQ spot-per-inch faxbased image.  ... 
doi:10.1145/169059.169445 dblp:conf/chi/JohnsonJKRC93 fatcat:ubjnlsykejaknhjz5oauy765vq

Development of an Automated Roughness Estimation Algorithm for Sidescan Imagery

Maura C. Lohrenz, Marlin L. Gendron
2007 OCEANS 2007 - Europe  
In repeated trials, results of the automated roughness algorithm correlated well (as high as 87%) with manual roughness estimations.  ...  Features such as pockmarks, sand ripples, and rocks on the seafloor are visible in SSI as bright spots ("brights") with adjacent shadows.  ...  In other words, a single shadow threshold value (i min ) suffices for more values of x than a single bright threshold value (i max ).  ... 
doi:10.1109/oceanse.2007.4302388 fatcat:7ot5xgp5tjclzjhw7ts2s5egti

A Study on Optical Character Recognition Techniques

Narendra Sahu, Manoj Sonkusare
2017 International Journal of Computational Science Information Technology and Control Engineering  
In general the alphabets are in the variety of pixel pictures and it could be either handwritten or stamped, of any series, shape or direction etc.  ...  In our survey we study on the various OCR techniques. In this paper we resolve and examine the hypothetical and numerical models of Optical Character Identification.  ...  in a bitmap format.  ... 
doi:10.5121/ijcsitce.2017.4101 fatcat:tvyygemmeng7hl7i34w5w34xnm

An old greek handwritten OCR system based on an efficient segmentation-free approach

K. Ntzios, B. Gatos, I. Pratikakis, T. Konidaris, S. J. Perantonis
2007 International Journal on Document Analysis and Recognition  
which are written in lowercase letters and originate from St.  ...  In this paper, we focus on the problem of recognizing Old Greek manuscripts and propose a novel recognition technique that has been tested in a large number of important historical manuscript collections  ...  In the case of historical documents, Manmatha and Croft [23] presented a method for word spotting wherein matching was based on the comparison of entire words rather than individual characters.  ... 
doi:10.1007/s10032-006-0031-z fatcat:vobtuts65bffvjn4rnm66fka5a

Ottoman archives explorer

Ismet Zeki Yalniz, Ismail Sengor Altingovde, Uvgur Güdükbay, Özgür Ulusoy
2009 ACM Journal on Computing and Cultural Heritage  
The prototype system provides CBR of document images using both example-based queries and a virtual keyboard to construct query words.  ...  In particular, sliding-window and histogram segmentation methods are coupled with recognition approaches using spatial features, neural networks, and a graph-based model.  ...  In Ataer and Duygulu [2006], a retrieval system for Ottoman documents is proposed that involves first segmenting lines and words in a document, and then comparing whole words while querying.  ... 
doi:10.1145/1658346.1658348 fatcat:kihwabab25b4lhajjoj2bwqqcq

Graphical information resources

Michael Lesk
1985 Proceedings of the 8th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '85  
Thexe is no an-o,~og of the simple ke~wor~ systems that hndle ,extual dvcuments in any subject area.  ...  Again, there are a variety of styles of data representation used in printing documents.  ...  This turns, for example "sum from 0 to inf x sub i" into with the items sum, from, to and in/ being reserved words.  ... 
doi:10.1145/253495.253504 dblp:conf/sigir/Lesk85 fatcat:dnlogk2mqfhvzftisikciosa3y

The University Licensing program (TULIP):

Jaco Zijlstra
1994 Serials: The Journal for the Serials Community  
document delivery systems, P o s W p t or SGML database files or network development.  ...  Each university receives, without charge during the project, the electronic full-text (bitmapped and ASCII) for those journals to which it subscribes in paper.  ... 
doi:10.1629/0702169 fatcat:kcirdvty5za3bjwmb7n7vmjcea


Berna Erol, Emilio Antúnez, Jonathan J. Hull
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
Given a document patch image, BWC utilizes the layout, i.e. relative locations, of word boxes in order to determine the original file, page, and the location on the page.  ...  Instead, we propose a document recognition algorithm that automatically determines the location of a patch of text in a large collection of document images given a small document image.  ...  For documents, a specially designed printer driver saves high resolution bitmap files for each printed page.  ... 
doi:10.1145/1459359.1459413 dblp:conf/mm/ErolAH08 fatcat:ytghlfxxufgd3hnmyerbv3kswm

On the applications of multimedia processing to communications

R.V. Cox, B.G. Haskell, Y. LeCun, B. Shahraray, L. Rabiner
1998 Proceedings of the IEEE  
The packet network is primarily accessed by client programs in PC's, and so it is inherently PC oriented and client/server driven.  ...  Today, the Internet (the largest of the existing packet networks) connects more than 40 million computers in some 140 countries.  ...  Howard (fax and image coding), A. Puri, J. Ostermann, T. Chen, and A.  ... 
doi:10.1109/5.664272 fatcat:yhn4kb3mmbctbbfus7br26oox4

Word spotting via spatial point processes

J.C. O'Neill, A.O. Hero, W.J. Williams
Proceedings of 3rd IEEE International Conference on Image Processing  
This paper presents a statistically based method for spotting target words in documents.  ...  This is accomplished by extracting the coordinate pairs, i.e. pixel locations, where the binary bitmap values of the word are non-zero.  ...  It would be useful if this process could be automated and work reliably on documents with di erent fonts, font sizes, and noise contamination, e.g. in faxed documents.  ... 
doi:10.1109/icip.1996.560733 dblp:conf/icip/ONeillHW96 fatcat:pz6e4ocxivhapimlockw4uvvaq

Developing and Publishing High-Quality Electronic Documents on CD-ROM [article]

Steve Cunningham
1997 Eurographics State of the Art Reports  
These notes explore the opportunities and challenges in this kind of publishing and help the reader evaluate the different kinds of approaches that may be taken in this area.  ...  Electronic publishing is the enterprise of producing content in electronic form that can be delivered by electronic media.  ...  search on the document or on a set of documents. • Play a movie that is in-line in the document. • Execute a link on the Web to an online document. • Use indexes to speed up word search (if the user is  ... 
doi:10.2312/egt.19971007 fatcat:m36r4jkb75hetgpx3q5ggv3rva

166 Attentional capture and oculomotor control

Arthur F. Kramer, Sowon Hahn, David E. Irwin, Jan Theeuwes
1998 International Journal of Psychophysiology  
Larger bitmap time intervals gave better results.  ... Can colour cues attract attention in a manner similar to those documented for luminance cues?  ... 
doi:10.1016/s0167-8760(98)90166-0 fatcat:7o5vmrk5zvbizd23bmpcbkrs7q

The Design of a Human Memory Prosthesis

M. Lamming
1994 Computer journal  
These guidelines define this new class of application, provide the basis for our continuing work in support of the problems of everyday office life, and offer a new challenge for computer systems research  ...  The next morning I saw my "name switch" said "IN". • Off to fax room with letter to be faxed-forgot to take the fax number (again!).  ...  So we're looking to see if we can find it. • I've just forgotten the word for "taking a responsibility". • Confusion about whether I had given Mary something (some documents).  ... 
doi:10.1093/comjnl/37.3.153 fatcat:zzebva5abzgg7jupyjzdmvilma
« Previous Showing results 1 — 15 out of 87 results